pith. sign in

← back to paper

Review history

arxiv: 2606.12634 · 2 revisions

Keep Policy Gradient in Charge: Sibling-Guided Credit Distillation for Long-Horizon Tool-Use Agents

  1. 2026-07-01 UNVERDICTED LOW v0.9.1-grok novelty 5.0
    30046 ms 5766 in 1356 out 2026-07-01T07:46:00.397824+00:00
  2. 2026-06-27 UNVERDICTED LOW v0.9.1-grok novelty 4.0
    27390 ms 5794 in 1090 out 2026-06-27T10:26:34.324134+00:00